Merge branch 'kvm-selftest' into kvm-master

- Cleanups for the perf test infrastructure and mapping hugepages

- Avoid contention on mmap_sem when the guests start to run

- Add event channel upcall support to xen_shinfo_test

tools/testing/selftests/kvm/access_tracking_perf_test.c

@@ -47,7 +47,7 @@
 #include "guest_modes.h"
 
 /* Global variable used to synchronize all of the vCPU threads. */
-static int iteration = -1;
+static int iteration;
 
 /* Defines what vCPU threads should do during a given iteration. */
 static enum {
@@ -215,12 +215,11 @@ static bool spin_wait_for_next_iteration(int *current_iteration)
 	return true;
 }
 
-static void *vcpu_thread_main(void *arg)
+static void vcpu_thread_main(struct perf_test_vcpu_args *vcpu_args)
 {
-	struct perf_test_vcpu_args *vcpu_args = arg;
 	struct kvm_vm *vm = perf_test_args.vm;
 	int vcpu_id = vcpu_args->vcpu_id;
-	int current_iteration = -1;
+	int current_iteration = 0;
 
 	while (spin_wait_for_next_iteration(&current_iteration)) {
 		switch (READ_ONCE(iteration_work)) {
@@ -235,8 +234,6 @@ static void *vcpu_thread_main(void *arg)
 
 		vcpu_last_completed_iteration[vcpu_id] = current_iteration;
 	}
-
-	return NULL;
 }
 
 static void spin_wait_for_vcpu(int vcpu_id, int target_iteration)
@@ -277,8 +274,7 @@ static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description)
 static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access,
 			  const char *description)
 {
-	perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1;
-	sync_global_to_guest(vm, perf_test_args);
+	perf_test_set_wr_fract(vm, (access == ACCESS_READ) ? INT_MAX : 1);
 	iteration_work = ITERATION_ACCESS_MEMORY;
 	run_iteration(vm, vcpus, description);
 }
@@ -296,48 +292,16 @@ static void mark_memory_idle(struct kvm_vm *vm, int vcpus)
 	run_iteration(vm, vcpus, "Mark memory idle");
 }
 
-static pthread_t *create_vcpu_threads(int vcpus)
-{
-	pthread_t *vcpu_threads;
-	int i;
-
-	vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0]));
-	TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads.");
-
-	for (i = 0; i < vcpus; i++) {
-		vcpu_last_completed_iteration[i] = iteration;
-		pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main,
-			       &perf_test_args.vcpu_args[i]);
-	}
-
-	return vcpu_threads;
-}
-
-static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus)
-{
-	int i;
-
-	/* Set done to signal the vCPU threads to exit */
-	done = true;
-
-	for (i = 0; i < vcpus; i++)
-		pthread_join(vcpu_threads[i], NULL);
-}
-
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *params = arg;
 	struct kvm_vm *vm;
-	pthread_t *vcpu_threads;
 	int vcpus = params->vcpus;
 
 	vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, 1,
-				 params->backing_src);
+				 params->backing_src, !overlap_memory_access);
 
-	perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes,
-			      !overlap_memory_access);
-
-	vcpu_threads = create_vcpu_threads(vcpus);
+	perf_test_start_vcpu_threads(vcpus, vcpu_thread_main);
 
 	pr_info("\n");
 	access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory");
@@ -352,8 +316,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	mark_memory_idle(vm, vcpus);
 	access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory");
 
-	terminate_vcpu_threads(vcpu_threads, vcpus);
-	free(vcpu_threads);
+	/* Set done to signal the vCPU threads to exit */
+	done = true;
+
+	perf_test_join_vcpu_threads(vcpus);
 	perf_test_destroy_vm(vm);
 }
 

tools/testing/selftests/kvm/demand_paging_test.c

@@ -42,10 +42,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
 static size_t demand_paging_size;
 static char *guest_data_prototype;
 
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	int ret;
-	struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 	struct kvm_vm *vm = perf_test_args.vm;
 	struct kvm_run *run;
@@ -68,8 +67,6 @@ static void *vcpu_worker(void *data)
 	ts_diff = timespec_elapsed(start);
 	PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id,
 		       ts_diff.tv_sec, ts_diff.tv_nsec);
-
-	return NULL;
 }
 
 static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr)
@@ -282,7 +279,6 @@ struct test_params {
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *vcpu_threads;
 	pthread_t *uffd_handler_threads = NULL;
 	struct uffd_handler_args *uffd_args = NULL;
 	struct timespec start;
@@ -293,9 +289,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	int r;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
-				 p->src_type);
-
-	perf_test_args.wr_fract = 1;
+				 p->src_type, p->partition_vcpu_memory_access);
 
 	demand_paging_size = get_backing_src_pagesz(p->src_type);
 
@@ -304,12 +298,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		    "Failed to allocate buffer for guest data pattern");
 	memset(guest_data_prototype, 0xAB, demand_paging_size);
 
-	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
-	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
-			      p->partition_vcpu_memory_access);
-
 	if (p->uffd_mode) {
 		uffd_handler_threads =
 			malloc(nr_vcpus * sizeof(*uffd_handler_threads));
@@ -322,26 +310,15 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
 
 		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-			vm_paddr_t vcpu_gpa;
+			struct perf_test_vcpu_args *vcpu_args;
 			void *vcpu_hva;
 			void *vcpu_alias;
-			uint64_t vcpu_mem_size;
-
 
-			if (p->partition_vcpu_memory_access) {
-				vcpu_gpa = guest_test_phys_mem +
-					   (vcpu_id * guest_percpu_mem_size);
-				vcpu_mem_size = guest_percpu_mem_size;
-			} else {
-				vcpu_gpa = guest_test_phys_mem;
-				vcpu_mem_size = guest_percpu_mem_size * nr_vcpus;
-			}
-			PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-				       vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size);
+			vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
 
 			/* Cache the host addresses of the region */
-			vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
-			vcpu_alias = addr_gpa2alias(vm, vcpu_gpa);
+			vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa);
+			vcpu_alias = addr_gpa2alias(vm, vcpu_args->gpa);
 
 			/*
 			 * Set up user fault fd to handle demand paging
@@ -355,32 +332,18 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 					    pipefds[vcpu_id * 2], p->uffd_mode,
 					    p->uffd_delay, &uffd_args[vcpu_id],
 					    vcpu_hva, vcpu_alias,
-					    vcpu_mem_size);
+					    vcpu_args->pages * perf_test_args.guest_page_size);
 		}
 	}
 
-	/* Export the shared variables to the guest */
-	sync_global_to_guest(vm, perf_test_args);
-
 	pr_info("Finished creating vCPUs and starting uffd threads\n");
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
-
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &perf_test_args.vcpu_args[vcpu_id]);
-	}
-
+	perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
 	pr_info("Started all vCPUs\n");
 
-	/* Wait for the vcpu threads to quit */
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-		pthread_join(vcpu_threads[vcpu_id], NULL);
-		PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id);
-	}
-
+	perf_test_join_vcpu_threads(nr_vcpus);
 	ts_diff = timespec_elapsed(start);
-
 	pr_info("All vCPU threads joined\n");
 
 	if (p->uffd_mode) {
@@ -404,7 +367,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	perf_test_destroy_vm(vm);
 
 	free(guest_data_prototype);
-	free(vcpu_threads);
 	if (p->uffd_mode) {
 		free(uffd_handler_threads);
 		free(uffd_args);

tools/testing/selftests/kvm/dirty_log_perf_test.c

@@ -31,7 +31,7 @@ static bool host_quit;
 static int iteration;
 static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
 
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	int ret;
 	struct kvm_vm *vm = perf_test_args.vm;
@@ -41,7 +41,6 @@ static void *vcpu_worker(void *data)
 	struct timespec ts_diff;
 	struct timespec total = (struct timespec){0};
 	struct timespec avg;
-	struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 
 	run = vcpu_state(vm, vcpu_id);
@@ -83,8 +82,6 @@ static void *vcpu_worker(void *data)
 	pr_debug("\nvCPU %d dirtied 0x%lx pages over %d iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
 		vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id],
 		total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec);
-
-	return NULL;
 }
 
 struct test_params {
@@ -170,7 +167,6 @@ static void free_bitmaps(unsigned long *bitmaps[], int slots)
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *vcpu_threads;
 	struct kvm_vm *vm;
 	unsigned long **bitmaps;
 	uint64_t guest_num_pages;
@@ -186,9 +182,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	struct timespec clear_dirty_log_total = (struct timespec){0};
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size,
-				 p->slots, p->backing_src);
+				 p->slots, p->backing_src,
+				 p->partition_vcpu_memory_access);
 
-	perf_test_args.wr_fract = p->wr_fract;
+	perf_test_set_wr_fract(vm, p->wr_fract);
 
 	guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm);
 	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
@@ -203,25 +200,15 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		vm_enable_cap(vm, &cap);
 	}
 
-	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
-	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
-			      p->partition_vcpu_memory_access);
-
-	sync_global_to_guest(vm, perf_test_args);
-
 	/* Start the iterations */
 	iteration = 0;
 	host_quit = false;
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
 		vcpu_last_completed_iteration[vcpu_id] = -1;
 
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &perf_test_args.vcpu_args[vcpu_id]);
-	}
+	perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
 
 	/* Allow the vCPUs to populate memory */
 	pr_debug("Starting iteration %d - Populating\n", iteration);
@@ -290,8 +277,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	/* Tell the vcpu thread to quit */
 	host_quit = true;
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_join(vcpu_threads[vcpu_id], NULL);
+	perf_test_join_vcpu_threads(nr_vcpus);
 
 	avg = timespec_div(get_dirty_log_total, p->iterations);
 	pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
@@ -306,7 +292,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	}
 
 	free_bitmaps(bitmaps, p->slots);
-	free(vcpu_threads);
 	perf_test_destroy_vm(vm);
 }
 

tools/testing/selftests/kvm/dirty_log_test.c

@@ -115,7 +115,7 @@ static void guest_code(void)
 			addr = guest_test_virt_mem;
 			addr += (READ_ONCE(random_array[i]) % guest_num_pages)
 				* guest_page_size;
-			addr &= ~(host_page_size - 1);
+			addr = align_down(addr, host_page_size);
 			*(uint64_t *)addr = READ_ONCE(iteration);
 		}
 
@@ -737,14 +737,14 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	if (!p->phys_offset) {
 		guest_test_phys_mem = (vm_get_max_gfn(vm) -
 				       guest_num_pages) * guest_page_size;
-		guest_test_phys_mem &= ~(host_page_size - 1);
+		guest_test_phys_mem = align_down(guest_test_phys_mem, host_page_size);
 	} else {
 		guest_test_phys_mem = p->phys_offset;
 	}
 
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
-	guest_test_phys_mem &= ~((1 << 20) - 1);
+	guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20);
 #endif
 
 	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);

tools/testing/selftests/kvm/include/perf_test_util.h

@@ -8,6 +8,8 @@
 #ifndef SELFTEST_KVM_PERF_TEST_UTIL_H
 #define SELFTEST_KVM_PERF_TEST_UTIL_H
 
+#include <pthread.h>
+
 #include "kvm_util.h"
 
 /* Default guest test virtual memory offset */
@@ -18,6 +20,7 @@
 #define PERF_TEST_MEM_SLOT_INDEX	1
 
 struct perf_test_vcpu_args {
+	uint64_t gpa;
 	uint64_t gva;
 	uint64_t pages;
 
@@ -27,7 +30,7 @@ struct perf_test_vcpu_args {
 
 struct perf_test_args {
 	struct kvm_vm *vm;
-	uint64_t host_page_size;
+	uint64_t gpa;
 	uint64_t guest_page_size;
 	int wr_fract;
 
@@ -36,19 +39,15 @@ struct perf_test_args {
 
 extern struct perf_test_args perf_test_args;
 
-/*
- * Guest physical memory offset of the testing memory slot.
- * This will be set to the topmost valid physical address minus
- * the test memory size.
- */
-extern uint64_t guest_test_phys_mem;
-
 struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   uint64_t vcpu_memory_bytes, int slots,
-				   enum vm_mem_backing_src_type backing_src);
+				   enum vm_mem_backing_src_type backing_src,
+				   bool partition_vcpu_memory_access);
 void perf_test_destroy_vm(struct kvm_vm *vm);
-void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
-			   uint64_t vcpu_memory_bytes,
-			   bool partition_vcpu_memory_access);
+
+void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract);
+
+void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *));
+void perf_test_join_vcpu_threads(int vcpus);
 
 #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */

tools/testing/selftests/kvm/include/test_util.h

@@ -104,6 +104,7 @@ size_t get_trans_hugepagesz(void);
 size_t get_def_hugetlb_pagesz(void);
 const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i);
 size_t get_backing_src_pagesz(uint32_t i);
+bool is_backing_src_hugetlb(uint32_t i);
 void backing_src_help(const char *flag);
 enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name);
 long get_run_delay(void);
@@ -117,4 +118,29 @@ static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t)
 	return vm_mem_backing_src_alias(t)->flag & MAP_SHARED;
 }
 
+/* Aligns x up to the next multiple of size. Size must be a power of 2. */
+static inline uint64_t align_up(uint64_t x, uint64_t size)
+{
+	uint64_t mask = size - 1;
+
+	TEST_ASSERT(size != 0 && !(size & (size - 1)),
+		    "size not a power of 2: %lu", size);
+	return ((x + mask) & ~mask);
+}
+
+static inline uint64_t align_down(uint64_t x, uint64_t size)
+{
+	uint64_t x_aligned_up = align_up(x, size);
+
+	if (x == x_aligned_up)
+		return x;
+	else
+		return x_aligned_up - size;
+}
+
+static inline void *align_ptr_up(void *x, size_t size)
+{
+	return (void *)align_up((unsigned long)x, size);
+}
+
 #endif /* SELFTEST_KVM_TEST_UTIL_H */

tools/testing/selftests/kvm/kvm_page_table_test.c

@@ -280,7 +280,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
 #ifdef __s390x__
 	alignment = max(0x100000, alignment);
 #endif
-	guest_test_phys_mem &= ~(alignment - 1);
+	guest_test_phys_mem = align_down(guest_test_virt_mem, alignment);
 
 	/* Set up the shared data structure test_args */
 	test_args.vm = vm;

tools/testing/selftests/kvm/lib/elf.c

@@ -157,8 +157,7 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename)
 			"memsize of 0,\n"
 			"  phdr index: %u p_memsz: 0x%" PRIx64,
 			n1, (uint64_t) phdr.p_memsz);
-		vm_vaddr_t seg_vstart = phdr.p_vaddr;
-		seg_vstart &= ~(vm_vaddr_t)(vm->page_size - 1);
+		vm_vaddr_t seg_vstart = align_down(phdr.p_vaddr, vm->page_size);
 		vm_vaddr_t seg_vend = phdr.p_vaddr + phdr.p_memsz - 1;
 		seg_vend |= vm->page_size - 1;
 		size_t seg_size = seg_vend - seg_vstart + 1;

tools/testing/selftests/kvm/lib/kvm_util.c

@@ -22,15 +22,6 @@
 
 static int vcpu_mmap_sz(void);
 
-/* Aligns x up to the next multiple of size. Size must be a power of 2. */
-static void *align(void *x, size_t size)
-{
-	size_t mask = size - 1;
-	TEST_ASSERT(size != 0 && !(size & (size - 1)),
-		    "size not a power of 2: %lu", size);
-	return (void *) (((size_t) x + mask) & ~mask);
-}
-
 int open_path_or_exit(const char *path, int flags)
 {
 	int fd;
@@ -191,15 +182,15 @@ const char *vm_guest_mode_string(uint32_t i)
 }
 
 const struct vm_guest_mode_params vm_guest_mode_params[] = {
-	{ 52, 48,  0x1000, 12 },
-	{ 52, 48, 0x10000, 16 },
-	{ 48, 48,  0x1000, 12 },
-	{ 48, 48, 0x10000, 16 },
-	{ 40, 48,  0x1000, 12 },
-	{ 40, 48, 0x10000, 16 },
-	{  0,  0,  0x1000, 12 },
-	{ 47, 64,  0x1000, 12 },
-	{ 44, 64,  0x1000, 12 },
+	[VM_MODE_P52V48_4K]	= { 52, 48,  0x1000, 12 },
+	[VM_MODE_P52V48_64K]	= { 52, 48, 0x10000, 16 },
+	[VM_MODE_P48V48_4K]	= { 48, 48,  0x1000, 12 },
+	[VM_MODE_P48V48_64K]	= { 48, 48, 0x10000, 16 },
+	[VM_MODE_P40V48_4K]	= { 40, 48,  0x1000, 12 },
+	[VM_MODE_P40V48_64K]	= { 40, 48, 0x10000, 16 },
+	[VM_MODE_PXXV48_4K]	= {  0,  0,  0x1000, 12 },
+	[VM_MODE_P47V64_4K]	= { 47, 64,  0x1000, 12 },
+	[VM_MODE_P44V64_4K]	= { 44, 64,  0x1000, 12 },
 };
 _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
 	       "Missing new mode params?");
@@ -879,9 +870,17 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	alignment = 1;
 #endif
 
+	/*
+	 * When using THP mmap is not guaranteed to returned a hugepage aligned
+	 * address so we have to pad the mmap. Padding is not needed for HugeTLB
+	 * because mmap will always return an address aligned to the HugeTLB
+	 * page size.
+	 */
 	if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
 		alignment = max(backing_src_pagesz, alignment);
 
+	ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz));
+
 	/* Add enough memory to align up if necessary */
 	if (alignment > 1)
 		region->mmap_size += alignment;
@@ -914,8 +913,13 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 		    "test_malloc failed, mmap_start: %p errno: %i",
 		    region->mmap_start, errno);
 
+	TEST_ASSERT(!is_backing_src_hugetlb(src_type) ||
+		    region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz),
+		    "mmap_start %p is not aligned to HugeTLB page size 0x%lx",
+		    region->mmap_start, backing_src_pagesz);
+
 	/* Align host address */
-	region->host_mem = align(region->mmap_start, alignment);
+	region->host_mem = align_ptr_up(region->mmap_start, alignment);
 
 	/* As needed perform madvise */
 	if ((src_type == VM_MEM_SRC_ANONYMOUS ||
@@ -958,7 +962,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 			    "mmap of alias failed, errno: %i", errno);
 
 		/* Align host alias address */
-		region->host_alias = align(region->mmap_alias, alignment);
+		region->host_alias = align_ptr_up(region->mmap_alias, alignment);
 	}
 }
 

tools/testing/selftests/kvm/lib/perf_test_util.c

@@ -10,21 +10,40 @@
 
 struct perf_test_args perf_test_args;
 
-uint64_t guest_test_phys_mem;
-
 /*
  * Guest virtual memory offset of the testing memory slot.
  * Must not conflict with identity mapped test code.
  */
 static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
 
+struct vcpu_thread {
+	/* The id of the vCPU. */
+	int vcpu_id;
+
+	/* The pthread backing the vCPU. */
+	pthread_t thread;
+
+	/* Set to true once the vCPU thread is up and running. */
+	bool running;
+};
+
+/* The vCPU threads involved in this test. */
+static struct vcpu_thread vcpu_threads[KVM_MAX_VCPUS];
+
+/* The function run by each vCPU thread, as provided by the test. */
+static void (*vcpu_thread_fn)(struct perf_test_vcpu_args *);
+
+/* Set to true once all vCPU threads are up and running. */
+static bool all_vcpu_threads_running;
+
 /*
  * Continuously write to the first 8 bytes of each page in the
  * specified region.
  */
 static void guest_code(uint32_t vcpu_id)
 {
-	struct perf_test_vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+	struct perf_test_args *pta = &perf_test_args;
+	struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_id];
 	uint64_t gva;
 	uint64_t pages;
 	int i;
@@ -37,9 +56,9 @@ static void guest_code(uint32_t vcpu_id)
 
 	while (true) {
 		for (i = 0; i < pages; i++) {
-			uint64_t addr = gva + (i * perf_test_args.guest_page_size);
+			uint64_t addr = gva + (i * pta->guest_page_size);
 
-			if (i % perf_test_args.wr_fract == 0)
+			if (i % pta->wr_fract == 0)
 				*(uint64_t *)addr = 0x0123456789ABCDEF;
 			else
 				READ_ONCE(*(uint64_t *)addr);
@@ -49,35 +68,81 @@ static void guest_code(uint32_t vcpu_id)
 	}
 }
 
+void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
+			   uint64_t vcpu_memory_bytes,
+			   bool partition_vcpu_memory_access)
+{
+	struct perf_test_args *pta = &perf_test_args;
+	struct perf_test_vcpu_args *vcpu_args;
+	int vcpu_id;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		vcpu_args = &pta->vcpu_args[vcpu_id];
+
+		vcpu_args->vcpu_id = vcpu_id;
+		if (partition_vcpu_memory_access) {
+			vcpu_args->gva = guest_test_virt_mem +
+					 (vcpu_id * vcpu_memory_bytes);
+			vcpu_args->pages = vcpu_memory_bytes /
+					   pta->guest_page_size;
+			vcpu_args->gpa = pta->gpa + (vcpu_id * vcpu_memory_bytes);
+		} else {
+			vcpu_args->gva = guest_test_virt_mem;
+			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
+					   pta->guest_page_size;
+			vcpu_args->gpa = pta->gpa;
+		}
+
+		vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+
+		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+			 vcpu_id, vcpu_args->gpa, vcpu_args->gpa +
+			 (vcpu_args->pages * pta->guest_page_size));
+	}
+}
+
 struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   uint64_t vcpu_memory_bytes, int slots,
-				   enum vm_mem_backing_src_type backing_src)
+				   enum vm_mem_backing_src_type backing_src,
+				   bool partition_vcpu_memory_access)
 {
+	struct perf_test_args *pta = &perf_test_args;
 	struct kvm_vm *vm;
 	uint64_t guest_num_pages;
+	uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src);
 	int i;
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	perf_test_args.host_page_size = getpagesize();
-	perf_test_args.guest_page_size = vm_guest_mode_params[mode].page_size;
+	/* By default vCPUs will write to memory. */
+	pta->wr_fract = 1;
+
+	/*
+	 * Snapshot the non-huge page size.  This is used by the guest code to
+	 * access/dirty pages at the logging granularity.
+	 */
+	pta->guest_page_size = vm_guest_mode_params[mode].page_size;
 
 	guest_num_pages = vm_adjust_num_guest_pages(mode,
-				(vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size);
+				(vcpus * vcpu_memory_bytes) / pta->guest_page_size);
 
-	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
+	TEST_ASSERT(vcpu_memory_bytes % getpagesize() == 0,
 		    "Guest memory size is not host page size aligned.");
-	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
+	TEST_ASSERT(vcpu_memory_bytes % pta->guest_page_size == 0,
 		    "Guest memory size is not guest page size aligned.");
 	TEST_ASSERT(guest_num_pages % slots == 0,
 		    "Guest memory cannot be evenly divided into %d slots.",
 		    slots);
 
+	/*
+	 * Pass guest_num_pages to populate the page tables for test memory.
+	 * The memory is also added to memslot 0, but that's a benign side
+	 * effect as KVM allows aliasing HVAs in meslots.
+	 */
 	vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES,
-				  (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size,
-				  0, guest_code, NULL);
+				  guest_num_pages, 0, guest_code, NULL);
 
-	perf_test_args.vm = vm;
+	pta->vm = vm;
 
 	/*
 	 * If there should be more memory in the guest test region than there
@@ -90,20 +155,18 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
 		    vcpu_memory_bytes);
 
-	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
-			      perf_test_args.guest_page_size;
-	guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1);
+	pta->gpa = (vm_get_max_gfn(vm) - guest_num_pages) * pta->guest_page_size;
+	pta->gpa = align_down(pta->gpa, backing_src_pagesz);
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
-	guest_test_phys_mem &= ~((1 << 20) - 1);
+	pta->gpa = align_down(pta->gpa, 1 << 20);
 #endif
-	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+	pr_info("guest physical test memory offset: 0x%lx\n", pta->gpa);
 
 	/* Add extra memory slots for testing */
 	for (i = 0; i < slots; i++) {
 		uint64_t region_pages = guest_num_pages / slots;
-		vm_paddr_t region_start = guest_test_phys_mem +
-			region_pages * perf_test_args.guest_page_size * i;
+		vm_paddr_t region_start = pta->gpa + region_pages * pta->guest_page_size * i;
 
 		vm_userspace_mem_region_add(vm, backing_src, region_start,
 					    PERF_TEST_MEM_SLOT_INDEX + i,
@@ -111,10 +174,15 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 	}
 
 	/* Do mapping for the demand paging memory slot */
-	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages);
+	virt_map(vm, guest_test_virt_mem, pta->gpa, guest_num_pages);
+
+	perf_test_setup_vcpus(vm, vcpus, vcpu_memory_bytes, partition_vcpu_memory_access);
 
 	ucall_init(vm, NULL);
 
+	/* Export the shared variables to the guest. */
+	sync_global_to_guest(vm, perf_test_args);
+
 	return vm;
 }
 
@@ -124,36 +192,60 @@ void perf_test_destroy_vm(struct kvm_vm *vm)
 	kvm_vm_free(vm);
 }
 
-void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
-			   uint64_t vcpu_memory_bytes,
-			   bool partition_vcpu_memory_access)
+void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract)
+{
+	perf_test_args.wr_fract = wr_fract;
+	sync_global_to_guest(vm, perf_test_args);
+}
+
+static void *vcpu_thread_main(void *data)
+{
+	struct vcpu_thread *vcpu = data;
+
+	WRITE_ONCE(vcpu->running, true);
+
+	/*
+	 * Wait for all vCPU threads to be up and running before calling the test-
+	 * provided vCPU thread function. This prevents thread creation (which
+	 * requires taking the mmap_sem in write mode) from interfering with the
+	 * guest faulting in its memory.
+	 */
+	while (!READ_ONCE(all_vcpu_threads_running))
+		;
+
+	vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_id]);
+
+	return NULL;
+}
+
+void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *))
 {
-	vm_paddr_t vcpu_gpa;
-	struct perf_test_vcpu_args *vcpu_args;
 	int vcpu_id;
 
+	vcpu_thread_fn = vcpu_fn;
+	WRITE_ONCE(all_vcpu_threads_running, false);
+
 	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
-		vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+		struct vcpu_thread *vcpu = &vcpu_threads[vcpu_id];
 
-		vcpu_args->vcpu_id = vcpu_id;
-		if (partition_vcpu_memory_access) {
-			vcpu_args->gva = guest_test_virt_mem +
-					 (vcpu_id * vcpu_memory_bytes);
-			vcpu_args->pages = vcpu_memory_bytes /
-					   perf_test_args.guest_page_size;
-			vcpu_gpa = guest_test_phys_mem +
-				   (vcpu_id * vcpu_memory_bytes);
-		} else {
-			vcpu_args->gva = guest_test_virt_mem;
-			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
-					   perf_test_args.guest_page_size;
-			vcpu_gpa = guest_test_phys_mem;
-		}
+		vcpu->vcpu_id = vcpu_id;
+		WRITE_ONCE(vcpu->running, false);
 
-		vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+		pthread_create(&vcpu->thread, NULL, vcpu_thread_main, vcpu);
+	}
 
-		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-			 vcpu_id, vcpu_gpa, vcpu_gpa +
-			 (vcpu_args->pages * perf_test_args.guest_page_size));
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		while (!READ_ONCE(vcpu_threads[vcpu_id].running))
+			;
 	}
+
+	WRITE_ONCE(all_vcpu_threads_running, true);
+}
+
+void perf_test_join_vcpu_threads(int vcpus)
+{
+	int vcpu_id;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++)
+		pthread_join(vcpu_threads[vcpu_id].thread, NULL);
 }

tools/testing/selftests/kvm/lib/test_util.c

@@ -283,6 +283,11 @@ size_t get_backing_src_pagesz(uint32_t i)
 	}
 }
 
+bool is_backing_src_hugetlb(uint32_t i)
+{
+	return !!(vm_mem_backing_src_alias(i)->flag & MAP_HUGETLB);
+}
+
 static void print_available_backing_src_types(const char *prefix)
 {
 	int i;

tools/testing/selftests/kvm/memslot_modification_stress_test.c

@@ -36,11 +36,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
 
 static bool run_vcpus = true;
 
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	int ret;
-	struct perf_test_vcpu_args *vcpu_args =
-		(struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 	struct kvm_vm *vm = perf_test_args.vm;
 	struct kvm_run *run;
@@ -59,8 +57,6 @@ static void *vcpu_worker(void *data)
 			    "Invalid guest sync status: exit_reason=%s\n",
 			    exit_reason_str(run->exit_reason));
 	}
-
-	return NULL;
 }
 
 struct memslot_antagonist_args {
@@ -80,7 +76,7 @@ static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay,
 	 * Add the dummy memslot just below the perf_test_util memslot, which is
 	 * at the top of the guest physical address space.
 	 */
-	gpa = guest_test_phys_mem - pages * vm_get_page_size(vm);
+	gpa = perf_test_args.gpa - pages * vm_get_page_size(vm);
 
 	for (i = 0; i < nr_modifications; i++) {
 		usleep(delay);
@@ -100,29 +96,15 @@ struct test_params {
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *vcpu_threads;
 	struct kvm_vm *vm;
-	int vcpu_id;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
-				 VM_MEM_SRC_ANONYMOUS);
-
-	perf_test_args.wr_fract = 1;
-
-	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
-	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
-			      p->partition_vcpu_memory_access);
-
-	/* Export the shared variables to the guest */
-	sync_global_to_guest(vm, perf_test_args);
+				 VM_MEM_SRC_ANONYMOUS,
+				 p->partition_vcpu_memory_access);
 
 	pr_info("Finished creating vCPUs\n");
 
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &perf_test_args.vcpu_args[vcpu_id]);
+	perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
 
 	pr_info("Started all vCPUs\n");
 
@@ -131,16 +113,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	run_vcpus = false;
 
-	/* Wait for the vcpu threads to quit */
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_join(vcpu_threads[vcpu_id], NULL);
-
+	perf_test_join_vcpu_threads(nr_vcpus);
 	pr_info("All vCPU threads joined\n");
 
-	ucall_uninit(vm);
-	kvm_vm_free(vm);
-
-	free(vcpu_threads);
+	perf_test_destroy_vm(vm);
 }
 
 static void help(char *name)

tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c

@@ -24,8 +24,12 @@
 
 #define PVTIME_ADDR	(SHINFO_REGION_GPA + PAGE_SIZE)
 #define RUNSTATE_ADDR	(SHINFO_REGION_GPA + PAGE_SIZE + 0x20)
+#define VCPU_INFO_ADDR	(SHINFO_REGION_GPA + 0x40)
 
 #define RUNSTATE_VADDR	(SHINFO_REGION_GVA + PAGE_SIZE + 0x20)
+#define VCPU_INFO_VADDR	(SHINFO_REGION_GVA + 0x40)
+
+#define EVTCHN_VECTOR	0x10
 
 static struct kvm_vm *vm;
 
@@ -56,15 +60,44 @@ struct vcpu_runstate_info {
     uint64_t time[4];
 };
 
+struct arch_vcpu_info {
+    unsigned long cr2;
+    unsigned long pad; /* sizeof(vcpu_info_t) == 64 */
+};
+
+struct vcpu_info {
+        uint8_t evtchn_upcall_pending;
+        uint8_t evtchn_upcall_mask;
+        unsigned long evtchn_pending_sel;
+        struct arch_vcpu_info arch;
+        struct pvclock_vcpu_time_info time;
+}; /* 64 bytes (x86) */
+
 #define RUNSTATE_running  0
 #define RUNSTATE_runnable 1
 #define RUNSTATE_blocked  2
 #define RUNSTATE_offline  3
 
+static void evtchn_handler(struct ex_regs *regs)
+{
+	struct vcpu_info *vi = (void *)VCPU_INFO_VADDR;
+	vi->evtchn_upcall_pending = 0;
+
+	GUEST_SYNC(0x20);
+}
+
 static void guest_code(void)
 {
 	struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR;
 
+	__asm__ __volatile__(
+		"sti\n"
+		"nop\n"
+	);
+
+	/* Trigger an interrupt injection */
+	GUEST_SYNC(0);
+
 	/* Test having the host set runstates manually */
 	GUEST_SYNC(RUNSTATE_runnable);
 	GUEST_ASSERT(rs->time[RUNSTATE_runnable] != 0);
@@ -153,7 +186,7 @@ int main(int argc, char *argv[])
 
 	struct kvm_xen_vcpu_attr vi = {
 		.type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO,
-		.u.gpa = SHINFO_REGION_GPA + 0x40,
+		.u.gpa = VCPU_INFO_ADDR,
 	};
 	vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &vi);
 
@@ -163,6 +196,16 @@ int main(int argc, char *argv[])
 	};
 	vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &pvclock);
 
+	struct kvm_xen_hvm_attr vec = {
+		.type = KVM_XEN_ATTR_TYPE_UPCALL_VECTOR,
+		.u.vector = EVTCHN_VECTOR,
+	};
+	vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &vec);
+
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+	vm_install_exception_handler(vm, EVTCHN_VECTOR, evtchn_handler);
+
 	if (do_runstate_tests) {
 		struct kvm_xen_vcpu_attr st = {
 			.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR,
@@ -171,9 +214,14 @@ int main(int argc, char *argv[])
 		vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st);
 	}
 
+	struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR);
+	vinfo->evtchn_upcall_pending = 0;
+
 	struct vcpu_runstate_info *rs = addr_gpa2hva(vm, RUNSTATE_ADDR);
 	rs->state = 0x5a;
 
+	bool evtchn_irq_expected = false;
+
 	for (;;) {
 		volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
 		struct ucall uc;
@@ -193,16 +241,21 @@ int main(int argc, char *argv[])
 			struct kvm_xen_vcpu_attr rst;
 			long rundelay;
 
-			/* If no runstate support, bail out early */
-			if (!do_runstate_tests)
-				goto done;
-
-			TEST_ASSERT(rs->state_entry_time == rs->time[0] +
-				    rs->time[1] + rs->time[2] + rs->time[3],
-				    "runstate times don't add up");
+			if (do_runstate_tests)
+				TEST_ASSERT(rs->state_entry_time == rs->time[0] +
+					    rs->time[1] + rs->time[2] + rs->time[3],
+					    "runstate times don't add up");
 
 			switch (uc.args[1]) {
-			case RUNSTATE_running...RUNSTATE_offline:
+			case 0:
+				evtchn_irq_expected = true;
+				vinfo->evtchn_upcall_pending = 1;
+				break;
+
+			case RUNSTATE_runnable...RUNSTATE_offline:
+				TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen");
+				if (!do_runstate_tests)
+					goto done;
 				rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT;
 				rst.u.runstate.state = uc.args[1];
 				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
@@ -236,6 +289,10 @@ int main(int argc, char *argv[])
 					sched_yield();
 				} while (get_run_delay() < rundelay);
 				break;
+			case 0x20:
+				TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ");
+				evtchn_irq_expected = false;
+				break;
 			}
 			break;
 		}